Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15563
    Prev
    Next
    INDEX
    Explanations

    phrases related to time spent or duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating duration or the concept of 'most of' in relation to time or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.80
    artisan
    -0.72
    untled
    -0.64
    idespread
    -0.57
     opio
    -0.55
     pedest
    -0.54
     Engineers
    -0.53
     Malays
    -0.53
    ocrats
    -0.53
    20439
    -0.52
    POSITIVE LOGITS
     eternity
    1.13
    urations
    0.83
     summer
    0.81
    morning
    0.81
    imester
    0.80
     summers
    0.79
    uesday
    0.79
    idays
    0.77
     duration
    0.76
     winters
    0.74
    Activations Density 0.090%

    No Known Activations